Profile

A computer science researcher and product owner who works on systems that have to scale.

I'm a Product Owner at p36 and a Research Associate and PhD student in the Scalable Software Systems group at TU Berlin, based in Berlin, Germany.

My research sits across distributed systems, software engineering, and benchmarking, and now clinical decision support through the TRANSFER project at TU Berlin. I like systems that have to hold up as they grow, which is usually where the harder problems are.

Lately I've been focused on AI safety in regulated settings: how to build the evidence that lets a team use AI and still answer for it. I care most about the cases where getting the systems right changes outcomes for real people.

Research Focus
Scalable SystemsSoftware EngineeringDistributed SystemsMedical InformaticsCloud Computing
01

Publications

Duet Instrumentation: An Agentic Approach to Improving Sensitivity in Cloud Service Benchmarking
Sebastian Koch, Nils Japke, David Bermbach
arXiv preprint · 2026PDF ↗Scholar ↗
Towards an Optimized Benchmarking Platform for CI/CD Pipelines
Nils Japke, Sebastian Koch, Hendrik Lukaszczyk, David Bermbach
IEEE IC2E · 2025PDF ↗Scholar ↗
Increasing Efficiency and Result Reliability of Continuous Benchmarking for FaaS Applications
Tim C. Rese, Nils Japke, Sebastian Koch, Tobias Pfandzelter, David Bermbach
IEEE IC2E · 2024PDF ↗Scholar ↗
02

Projects

gxpeval
A validation framework that lets regulated teams use AI accountably. It adds risk-tiered assurance, anytime-valid early stopping, qualified LLM judges, and a tamper-evident ALCOA+ audit trail, all on top of Inspect AI.
Open Source · Python
beforeyoudonate.org
Urging people to donate more effectively. Signatories include the co-founder of Lovable and Peter Singer.
Social Impact · Web